Accuracy Of Biomass Estimates Research Articles

Improving Forest Above-Ground Biomass Estimation by Integrating Individual Machine Learning Models

The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies have demonstrated that a single machine learning model can produce highly accurate estimations of forest AGB in many situations, efforts are still required to explore the possible improvement in forest AGB estimation for a specific scenario under study. This study aims to investigate the performance of novel ensemble machine learning methods for forest AGB estimation and analyzes whether these methods are affected by forest types, independent variables, and spatial autocorrelation. Four well-known machine learning models (CatBoost, LightGBM, random forest (RF), and XGBoost) were compared for forest AGB estimation in the study using eight scenarios devised on the basis of two study regions, two variable types, and two validation strategies. Subsequently, a hybrid model combining the strengths of these individual models was proposed for forest AGB estimation. The findings indicated that no individual model outperforms the others in all scenarios. The RF model demonstrates superior performance in scenarios 5, 6, and 7, while the CatBoost model shows the best performance in the remaining scenarios. Moreover, the proposed hybrid model consistently has the best performance in all scenarios in spite of some uncertainties. The ensemble strategy developed in this study for the hybrid model substantially improves estimation accuracy and exhibits greater stability, effectively addressing the challenge of model selection encountered in the forest AGB forecasting process.

Burrow Opening Measurements of Intertidal Macroinvertebrates from Optical Drone Images

Intertidal macroinvertebrates, such as crabs and mud shrimps, are invertebrates inhabiting the intertidal zone that are sufficiently large to be identified with the naked eye. Most intertidal macroinvertebrates typically construct burrows of various shapes in sediment to protect themselves from environmental extremes, with surface openings that reflect features of their species and body size. Especially circular burrow openings correlate with an organism’s body size; thus, measuring these openings can provide estimates of the organism’s size, weight, growth rate, and biomass. Traditional studies of these organisms have relied on field surveys, which are constrained by time, cost, and logistical limitations. This study introduces an innovative method for measuring the burrow opening diameters of intertidal macroinvertebrates using high-resolution optical images from a portable drone system. By leveraging the reflectance disparity between the sediment and burrow openings, this method facilitates the extraction and sizing of burrow openings. Our methodology was applied to three crab species known for their circular burrow opening: the red-clawed fiddler, the milky fiddler, and the ghost crab. Validation was confirmed through field data from the Mageumri and Sinduri tidal flats, South Korea. The method achieved a correlation coefficient (R2) of 0.94 and a root mean squared error (RMSE) of 1.68 mm across a diameter range of 6.21–33.59 mm. These findings suggest the potential of drone remote sensing systems as a non-invasive and efficacious approach for quantifying burrow sizes over extensive intertidal areas, thereby facilitating more accurate biomass estimations and surmounting the limitations of conventional field surveys. Future research could extend this method to additional species and further refine its precision.

Estimation of Rubber Plantation Biomass Based on Variable Optimization from Sentinel-2 Remote Sensing Imagery

The rapid, accurate, and non-destructive estimation of rubber plantation aboveground biomass (AGB) is essential for producers to forecast rubber yield and carbon storage. To enhance the estimation accuracy, an increasing number of remote sensing variables are incorporated into the development of multi-parameter models, which makes its practical application and the potential impact on predictive precision challenging due to the inclusion of non-essential or redundant variables. Therefore, this study systematically evaluated the performance of different parameter combinations derived from Sentinel-2 imagery, using variable optimization approaches with four machine learning algorithms (Random Forest Regression, RF; XGBoost Regression, XGBR; K Nearest Neighbor Regression, KNNR; and Support Vector Regression, SVR) for the estimation of the AGB of rubber plantations. The results indicate that RF achieved the best estimation accuracy (R2 = 0.86, RMSE = 15.77 Mg/ha) for predicting rubber plantation AGB when combined with Boruta-selected variables, outperforming other combinations (variable combinations obtained based on importance ranking, univariate combinations, and multivariate combinations). Our research findings suggest that the consideration of parameter-optimized remote sensing variables is advantageous for improving the estimation accuracy of forest biophysical parameters, when utilizing a large number of parameters for estimation.

Investigating Dual-Source Satellite Image Data and ALS Data for Estimating Aboveground Biomass

Accurate estimation of above-ground biomass (AGB) in forested areas is essential for studying forest ecological functions, surface carbon cycling, and global carbon balance. Over the past decade, models that harness the distinct features of multi-source remote sensing observations for estimating AGB have gained significant popularity. It is worth exploring the differences in model performance by using simple and fused data. Additionally, quantitative estimation of the impact of high-cost laser point clouds on satellite imagery of varying costs remains largely unexplored. To address these challenges, model performance and cost must be considered comprehensively. We propose a comprehensive assessment based on three perspectives (i.e., performance, potential and limitations) for four typical AGB-estimation models. First, different variables are extracted from the multi-source and multi-resolution data. Subsequently, the performance of four regression methods is tested for AGB estimation with diverse indicator combinations. Experimental results prove that the combination of multi-source data provides a highly accurate AGB regression model. The proposed regression and variables rating approaches can flexibly integrate other data sources for modeling. Furthermore, the data cost is discussed against the AGB model performance. Our study demonstrates the potential of using low-cost satellite data to provide a rough AGB estimation for larger areas, which can allow different remote sensing data to meet different needs of forest management decisions.

Estimation of water consumption volume and water efficiency in irrigated and rainfed agriculture based on the WaPOR database in Iran

ABSTRACT To evaluate the WaPOR model across the entire country of Iran, initially, 16 provinces located in four different climatic regions were selected for calculating and comparing the evapotranspiration using both the FAO-56 method and the WaPOR approach. The comparison of 10-day evapotranspiration values obtained from the FAO56 method and WaPOR demonstrates that the WaPOR model exhibits the highest correlation with FAO-56 values in semi-arid regions, with an R2 = 0.95 and an RMSE = 0.43. The analysis of evapotranspiration variations indicates that the evapotranspiration in the Caspian Sea and Zagros foothill regions has experienced more significant changes from 2015 to 2022. The annual analysis of net blue water productivity demonstrates that the net productivity in rainfed lands strongly depends on the precipitation received. Also, considering the importance of investigating the accuracy of biomass estimation, the correlation between the accuracy of biomass estimation and actual evapotranspiration was examined in four Iran climatic regions. Using the WaPOR model provides acceptable results for water consumption management and assessment in different regions and climates of Iran, particularly in agricultural lands. The WaPOR model can serve as a guide for determining reliable values of evapotranspiration and planning related to water resources in the agricultural sector in Iran.

Improving plot-level above ground biomass estimation in tropical Indian forests

Accurate plot-level estimates of above ground biomass (AGB) are crucial for reducing uncertainty in spatial AGB quantification, a key requirement for Reducing Emissions from Deforestation and Forest Degradation framework (REDD+) and achieving Intended Nationally Determined Contributions (INDC) goals. This study explores the impact of plot size, selection and use of height-diameter (H–D) model, and allometric models on plot-level AGB estimation in tropical Indian forests. We analyze a dataset of 8179 tree measurements from 51 one-hectare plots across four tropical sites to investigate these factors and improve estimation accuracy. Our findings highlight the importance of locally derived H–D models for superior accuracy. We propose two H–D models for improved plot-level AGB estimation accuracy in tropical Indian forests: a general model with a residual standard error (RSE) of 4.18 m and a forest type-specific model with a RSE of 3.65 m. These models outperform global models, which significantly underestimate tree height by up to 51.3% and overestimate by 43.4% across our sites. The developed H–D models were evaluated using spatial cross-validation to ensure broader applicability across Indian tropical forests. Further, we evaluated the impact of the choice of the allometric model on plot-level AGB estimation using the prevalent models (local destructive models by the Forest Survey of India and global pantropical models). Our results indicate minimal variability between the local destructive models and the pantropical model when height measurements are derived from this study's developed H–D models. We have also investigated the effect of plot size on plot-level AGB estimation using synthetic plots generated from 1-ha plot data. Notably, the relative error diminishes from approximately 22% to about 5% as plot size increases from 0.04 ha (20x20m) to 0.49 ha (70x70m) across all sites, and we recommend field plots of size ≥0.5 ha for AGB mapping over Tropical Indian Forests. By making this data publicly available, this study paves the way for more accurate spatial AGB mapping in tropical Indian forests, ultimately contributing to better forest management.

Comparative Study of Single-Wood Biomass Model at Plot Level Based on Multi-Source LiDAR

Forests play an important role in promoting carbon cycling and mitigating the urban heat island effect as one of the world’s major carbon storages. Scientifically quantifying tree biomass is the basis for assessing tree carbon storage and other ecosystem functions. In this study, a sample plot of Populus tomentosa plantation in the Olympic Forest Park in Beijing was selected as the research object. Point cloud data from three types of laser scanners, including terrestrial laser scanner (TLS), backpack laser scanner (BLS), and handheld laser scanner (HLS), were used to estimate the biomass of single tree trunks, branches, leaves, and aboveground total biomass based on the Allometric Biomass Model (ABM) and Advanced Quantitative Structure Model (AdQSM). The following conclusions were drawn from the estimation results: (1) For the three types of laser scanner point clouds, the biomass estimation values obtained using the AdQSM model were generally higher than those obtained using the Allometric Biomass Model. However, the estimation values obtained using the two models were similar, especially for tree trunks and total biomass. (2) For total biomass and individual biomass components of single trees, the results obtained from handheld and terrestrial laser scanner point clouds are consistent; however, they show some differences from the results obtained from backpack-mounted point clouds. This study further enriches the methodological system for estimating forest biomass, providing a theoretical basis and reference for more accurate estimates of forest biomass and more sustainable forest management.

Toward a More Robust Estimation of Forest Biomass Carbon Stock and Carbon Sink in Mountainous Region: A Case Study in Tibet, China

Mountainous forests are pivotal in the global carbon cycle, serving as substantial reservoirs and sinks of carbon. However, generating a reliable estimate remains a considerable challenge, primarily due to the lack of representative in situ measurements and proper methods capable of addressing their complex spatial variation. Here, we proposed a deep learning-based method that combines Residual convolutional neural networks (ResNet) with in situ measurements, microwave (Sentinel-1 and VOD), and optical data (Sentinel-2 and Landsat) to estimate forest biomass and track its change over the mountainous regions. Our approach, integrating in situ measurements across representative elevations with multi-source remote sensing images, significantly improves the accuracy of biomass estimation in Tibet’s complex mountainous forests (R2 = 0.80, root mean squared error = 15.8 MgC ha−1). Moreover, ResNet, which addresses the vanishing gradient problem in deep neural networks by introducing skip connections, enables the extraction of complex spatial patterns from limited datasets, outperforming traditional optical-based or pixel-based methods. The mean value of forest biomass was estimated as 162.8 ± 21.3 MgC ha−1, notably higher than that of forests at comparable latitudes or flat regions in China. Additionally, our findings revealed a substantial forest biomass carbon sink of 3.35 TgC year−1 during 2015–2020, which is largely underestimated by previous estimates, mainly due to the underestimation of mountainous carbon stock. The significant carbon density, combined with the underestimated carbon sink in mountainous regions, emphasizes the urgent need to reassess mountain forests to better approximate the global carbon budget.

Decadal changes in biomass and distribution of key fisheries species on Newfoundland's Grand Banks.

Canadian fisheries management has embraced the precautionary approach and the incorporation of ecosystem information into decision-making processes. Accurate estimation of fish stock biomass is crucial for ensuring sustainable exploitation of marine resources. Spatio-temporal models can provide improved indices of biomass as they capture spatial and temporal correlations in data and can account for environmental factors influencing biomass distributions. In this study, we developed a spatio-temporal generalized additive model (st-GAM) to investigate the relationships between bottom temperature, depth, and the biomass of three key fished species on The Grand Banks: snow crab (Chionoecetes opilio), yellowtail flounder (Limanda ferruginea), and Atlantic cod (Gadus morhua). Our findings revealed changes in the centre of gravity of Atlantic cod that could be related to a northern shift of the species within the Grand Banks or to a faster recovery of the 2J3KL stock. Atlantic cod also displayed hyperaggregation behaviour with the species showing a continuous distribution over the Grand Banks when biomass is high. These findings suggest a joint stock assessment between the 2J3KL and 3NO stocks would be advisable. However, barriers may need to be addressed to achieve collaboration between the two distinct regulatory bodies (i.e., DFO and NAFO) in charge of managing the stocks. Snow crab and yellowtail flounder centres of gravity have remained relatively constant over time. We also estimated novel indices of biomass, informed by environmental factors. Our study represents a step towards ecosystem-based fisheries management for the highly dynamic Grand Banks.

A Multi-Scale Forest Above-Ground Biomass Mapping Approach: Employing a Step-by-Step Spatial Downscaling Method with Bias-Corrected Ensemble Machine Learning

The accurate estimation of forest above-ground biomass (AGB) is vital for monitoring changes in forest carbon sinks. However, the spatial heterogeneity of AGB, coupled with inherent uncertainties, poses challenges in acquiring high-quality AGBs. This study introduced a bias-corrected ensemble machine learning (ML) algorithm for AGB downscaling that integrated a ML for AGB mapping with another for residual mapping. The accuracies of six bias-corrected ensemble ML algorithms were evaluated at resolutions of 0.05°, 0.025°, and 0.01°. Moreover, a step-by-step downscaling (SBSD) method was introduced, utilizing bias-corrected ensemble ML algorithms to downscale AGB from 0.1° to 0.05°, 0.025°, and 0.01° resolutions and was compared with the direct downscaling (DD) at three scales. A comparative analysis was conducted in the Daxing’anling Mountains and Xiaoxing’anling Mountains. AGB and corresponding uncertainty maps at three scales were generated using SBSD. The results showed that the efficacy of the XGBoost-based AGB model combined with the random forest-based residual correction model was superior. Spatial patterns in AGB maps generated by SBSD and DD were found to be similar. Notably, SBSD yielded enhanced accuracy in the Daxing’anling Mountains with complex topography, while both performed comparably in the Xiaoxing’anling Mountains with milder topography, highlighting SBSD’s advantages in high heterogeneity areas.

Site-Species Allometry Equation for Theobroma cacao L. Biomass Estimation in Agroforestry Systems of Cameroon

The accuracy of biomass estimates through mathematical expressions remains essential for the sustainability of the REDD+ process. The objective of this research was to develop allometric models by site species to evaluate the biomass of Theobroma cacao in agroforestry systems in the Central Region of Cameroon. Biomass data were obtained by the destructive method on a sample of 50 trees (5 cm ≤ D ≤ 27 cm). Allometric models were developed using aboveground (AGB), belowground (BGB), and total biomass (TB) as dependent variables and tree dendrometric parameters as independent variables. Nine linear models were adjusted based on the Akaike information criterion (AIC), residual standard error (RSE), coefficient of determination (R2), and various statistical tests including the normality test, heterogeneity, and autocorrelation for the analysis of residuals. The different results show that only the diameter appears to be a good predictor of biomass with an R2 greater than 0.94, 0.85, and 0.95, respectively, for aboveground biomass (M1: ln B = −1.613 + 1.83 × ln (D)), belowground biomass (M1: ln B = −2.611 + 1.65 × ln (D)), and total biomass (M1: ln B = −1.297 + 1.79 × ln (D)). Incorporating crown diameter and height into the models slightly improved the quality of adjusted. Comparison of the models in this study with pantropical equations previously used to estimate Theobroma cacao biomass shows that the models in this study provide a better estimate. The allometric equations developed in this work to estimate the AGB, BGB, and TB of Theobroma cacao can be used under the same environmental conditions to accurately predict the biomass accumulated in agroforestry systems by this species and thus allow the implementation of activities aimed at reducing emissions from deforestation and degradation (REDD+) for the benefit of local communities through the carbon market.

3D photogrammetry and deep‐learning deliver accurate estimates of epibenthic biomass

Abstract Accurate biomass estimates are key to understanding a wide variety of ecological functions. In marine systems, epibenthic biomass estimates have traditionally relied on either destructive/extractive methods that are limited to horizontal soft‐sediment environments, or simplistic geometry‐based biomass conversions that are unsuitable for more complex morphologies. Consequently, there is a requirement for non‐destructive, higher‐accuracy methods that can be used in an array of environments, targeting more morphologically diverse taxa, and at ecological relevant scales. We used a combination of 3D photogrammetry, convolutional neural network (CNN) automated taxonomic identification, and taxa‐specific biovolume:biomass calibrations to test the viability of estimating biomass of three species of morphologically complex epibenthic taxa from in situ stereo 2D source imagery. Our trained CNN produced accurate and reliable annotations of our target taxa across a wide range of conditions. When incorporated into photogrammetric 3D models of underwater surveys, we were able to automatically isolate our three target taxa from their environment, producing biovolume measurements that had respective mean similarities of 99%, 102% and 120% of those obtained from human annotators. When combined with taxa‐specific biovolume:biomass calibration values, we produced biomass estimates of 88%, 125% and 133% mean similarity to that of the ‘true’ biomass of the respective taxa. Our methodology provides a highly reliable and efficient method for estimating epibenthic biomass of morphologically complex taxa using non‐destructive 2D imagery. This approach can be applied to a variety of environments and photo/video survey approaches (e.g. SCUBA, ROV, AUV) and is especially valuable in spatially extensive surveys where manual approaches are prohibitively time‐consuming.

Forest Aboveground Biomass Estimation Using Multisource Remote Sensing Data and Deep Learning Algorithms: A Case Study over Hangzhou Area in China

The accurate estimation of forest aboveground biomass is of great significance for forest management and carbon balance monitoring. Remote sensing instruments have been widely applied in forest parameters inversion with wide coverage and high spatiotemporal resolution. In this paper, the capability of different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 and Landsat-8) and various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), in aboveground forest biomass estimation. In particular, based on the forest inventory data of Hangzhou in China, the Random Forest (RF), Convolutional Neural Network (CNN) and Convolutional Neural Networks Long Short-Term Memory Networks (CNN-LSTM) algorithms were deployed to construct the forest biomass estimation models, respectively. The estimate accuracies were evaluated under the different configurations of images and methods. The results show that for the SAR data, ALOS-2 has a higher biomass estimation accuracy than the GaoFen-3 and Sentinel-1. Moreover, the GaoFen-6 data is slightly worse than Sentinel-2 and Landsat-8 optical data in biomass estimation. In contrast with the single source, integrating multisource data can effectively enhance accuracy, with improvements ranging from 5% to 10%. The CNN-LSTM generally performs better than CNN and RF, regardless of the data used. The combination of CNN-LSTM and multisource data provided the best results in this case and can achieve the maximum R2 value of up to 0.74. It was found that the majority of the biomass values in the study area in 2018 ranged from 60 to 90 Mg/ha, with an average value of 64.20 Mg/ha.

Forest carbon stock-based bioeconomy: Mixed models improve accuracy of tree biomass estimates

Tree biomass and carbon stock continue to be the most important contributors to a forest-based bioeconomy. Accurate estimation of tree biomass and carbon stock therefore is crucial for planning a sustainable bioeconomy based on sustained forest bioresource production and harvest. Precise carbon accounting is also of fundamental importance for a green carbon market as well as for an improved model of quantitative global carbon cycle. However, estimating biomass and carbon at a large spatial scale without causing significant environmental disruption has been posing a methodological challenge necessitating to evolve a robust yet accurate estimation method. Although forest-specific generalized allometric models are the most widely used method to estimate forest tree biomass and carbon stock, these either under- or over-estimate the values, particularly in mixed-species forests. To address this challenge, we employed mixed equations that included species-specific models or available models for a sister species that provided a more conservative estimate of stand-level tree biomass and carbon compared to the generalized equations. We gathered primary data on tree girth and height at the stand level from sub-tropical and temperate forests of Tawang river basin, Arunachal Pradesh, India for validation. We compiled 32 equations comprising 27 species-specific and 5 forest-specific generalized models from a global dataset of allometric models. The outputs from the mixed models were comparable with the results of the harvest studies conducted by other researchers in similar forest types validating the efficacy of mixed models at a landscape scale.

Improving potato AGB estimation to mitigate phenological stage impacts through depth features from hyperspectral data

The accurate estimation of above ground biomass (AGB) is valuable in grasping the status of potato growth and assessing yield. Spectral analysis techniques play an important role in AGB estimation by virtue of its non-destructive and rapid advantages. However, the models constructed based on spectral features at the entire growth stages due to differences in phenological stages, such as vegetation indices (VIs) and locations at fixed wavelengths, can be not applicable to single growth stages. Therefore, the main objective of this study is to improve the applicability of the AGB estimation model to mitigate the impacts of phenological stages by mining depth features from hyperspectral data. The canopy hyperspectral and AGB data of potato tuber formation, tuber growth and starch accumulation stages were measured in 2017–2019. The acquired canopy hyperspectral reflectance was smoothed by Savitzky-Golay (SG) filter, and the green edge (GE), the red edge (RE), red edge chlorophyll index (CIred-edge), optimized soil adjusted vegetation index (OSAVI), green normalized difference vegetation index (GNDVI), and normalized difference vegetation index (NDVI) were extracted. The spectral changes were analyzed at different growth stages of each year. To obtain features in response to AGB changes, a new approach is proposed to analyze the hidden depth features between sensitive wavelengths by combining a successive projections algorithm (SPA) and a long-short-term memory network (LSTM). The AGB estimation models were constructed by partial least squares regression (PLSR) based on traditional VIs + GE + RE, full spectrum, sensitive wavelengths obtained by SPA, and depth features obtained by SPA-LSTM. The results showed that GE, RE and VIs alone explained only 24 %-36 % of the variation in AGB. The accuracy of estimating AGB at sensitive wavelengths obtained after SPA was higher (R2 = 0.70, RMSE = 406 kg/hm2, and NRMSE = 27.14 %) than that of conventional VIs + GE + RE (R2 = 0.51, RMSE = 536 kg/hm2, and NRMSE = 35.81 %) and full spectrum (R2 = 0.63, RMSE = 452 kg/hm2, and NRMSE = 30.19 %) in the three-year dataset. The depth features extracted by the SPA-LSTM method proposed in this study achieved the best AGB estimation (R2 = 0.82, RMSE = 318 kg/hm2, and NRMSE = 21.25 %). The applicability of the model was validated in different years and growth stages. The R2 of each year was in the range of 0.48–0.77, the RMSE was in the range of 290–367 kg/hm2, and the NRMSE was in the range of 16.69 %-25.81 %. The R2 of each growth stage within three year was in the range of 0.48–0.78, the RMSE was in the range of 184–386 kg/hm2, and the NRMSE was in the range of 14.91 %-29.45 %. The method proposed in this study mitigates the impacts of phenological stage and improves the robustness and accuracy of the AGB estimation model, which provides remote sensing technical support for realizing potato growth monitoring and yield assessment in the field.

UAV-LiDAR Integration with Sentinel-2 Enhances Precision in AGB Estimation for Bamboo Forests

Moso bamboo forests, recognized as a distinctive and significant forest resource in subtropical China, contribute substantially to efficient carbon sequestration. The accurate assessment of the aboveground biomass (AGB) in Moso bamboo forests is crucial for evaluating their impact on the carbon balance within forest ecosystems at a regional scale. In this study, we focused on the Moso bamboo forest located in Shanchuan Township, Zhejiang Province, China. The primary objective was to utilize various data sources, namely UAV-LiDAR (UL), Sentinel-2 (ST), and a combination of UAV-LiDAR with Sentinel-2 (UL + ST). Employing the Boruta algorithm, we carefully selected characterization variables for analysis. Our investigation delved into establishing correlations between UAV-LiDAR characterization parameters, Sentinel-2 feature parameters, and the aboveground biomass (AGB) of the Moso bamboo forest. Ground survey data on Moso bamboo forest biomass served as the basis for our analysis. To enhance the accuracy of AGB estimation in the Moso bamboo forest, we employed three distinct modeling techniques: multivariate linear regression (MLR), support vector regression (SVR), and random forest (RF). Through this approach, we aimed to compare the impact of different data sources and modeling methods on the precision of AGB estimation in the studied bamboo forest. This study revealed that (1) the point cloud intensity of UL, the variables of canopy cover (CC), gap fraction (GF), and leaf area index (LAI) reflect the structure of Moso bamboo forests, and the variables indicating the height of the forest stand (AIH1, AIHiq, and Hiq) had a significant effect on the AGB of Moso bamboo forests, significantly impact Moso bamboo forest AGB. Vegetation indices such as DVI and SAVI in ST also exert a considerable effect on Moso bamboo forest AGB. (2) AGB estimation models constructed based on UL consistently demonstrated higher accuracy compared with ST, achieving R2 values exceeding 0.7. Regardless of the model used, UL consistently delivered superior accuracy in Moso bamboo forest AGB estimation, with RF achieving the highest precision at R2 = 0.88. (3) Integration of ST with UL substantially improved the accuracy of AGB estimation for Moso bamboo forests across all three models. Specifically, using RF, the accuracy of AGB estimation increased by 97.7%, with R2 reaching 0.89 and RMSE reduced by 124.4%. As a result, the incorporation of LiDAR data, which reflects the stand structure, has proven to enhance the accuracy of aboveground biomass (AGB) estimation in Moso bamboo forests when combined with multispectral remote sensing data. This integration serves as an effective solution to address the limitations of single optical remote sensing methods, which often suffer from signal saturation, leading to lower accuracy in estimating Moso bamboo forest biomass. This approach offers a novel perspective and opens up new possibilities for improving the precision of Moso bamboo forest biomass estimation through the utilization of multiple remote sensing sources.

Early‐season biomass and weather enable robust cereal rye cover crop biomass predictions

AbstractFarmers need accurate estimates of winter cover crop biomass to make informed decisions on termination timing or to estimate potential release of nitrogen from cover crop residues to subsequent cash crops. Utilizing data from an extensive experiment across 11 states from 2016 to 2020, this study explores the most reliable predictors for determining cereal rye cover crop biomass at the time of termination. Our findings demonstrate a strong relationship between early‐season and late‐season cover crop biomass. Employing a random forest model, we predicted late‐season cereal rye biomass with a margin of error of approximately 1,000 kg ha−1 based on early‐season biomass, growing degree days, cereal rye planting and termination dates, photosynthetically active radiation, precipitation, and site coordinates as predictors. Our results suggest that similar modeling approaches could be combined with remotely sensed early‐season biomass estimations to improve the accuracy of predicting winter cover crop biomass at termination for decision support tools.Core Ideas Cereal rye winter cover crop biomass modeled on data from 35 site‐years. We found a strong relationship between early and late‐season biomass. Random forest model with early‐season biomass and weather data performed well. Similar approach could improve decision support tools for cover crop management.

Assessing the effect of ensemble learning algorithms and validation approach on estimating forest aboveground biomass: a case study of natural secondary forest in Northeast China

ABSTRACT Accurate estimation of forest aboveground biomass is essential for the assessment of regional carbon cycle and the climate change in the terrestrial ecosystem. Currently, ensemble learning algorithms and cross-validation methods have been widely applied to estimate regional forest Above Ground Biomass (AGB). However, the effects of ensemble learning algorithms, validation methods, and their interactions on forest AGB estimation were rarely investigated. Based on Landsat 8 Operational Land Imager (OLI) imagery, Airborne Laser Scanning (ALS) data and China’s National Forest Continuous Inventory data, this study explored the effects of five ensemble learning algorithms, including Simple Averaging (SA), Weighted Averaging (WA), Stacked Generalization (SG), Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and two validation approaches (i.e. 10-fold and leave-one-out cross-validation) on the AGB estimation of the Natural Secondary Forests (NSFs) in northeast China. The results revealed that the ensemble learning algorithms that combine heterogenous-based models (i.e. SA, WA, SG) generally produced higher accuracy than the base models (i.e. Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Convolutional Neural Network (CNN)). Among all ensemble learning algorithms, the SG algorithm has the highest accuracy whereas the XGBoost algorithm has the lowest accuracy. Although prediction models considerably impact the accuracy of AGB estimation, the validation approach also plays a non-negligible role in AGB estimation. The leave-one-out cross-validation produced much higher accuracy than the 10-fold cross-validation using the same prediction model and tends to generate over-optimistic AGB estimates compared to 10-fold cross-validation, especially for the averaging and stacking ensemble learning algorithms (i.e. SA, WA, SG). This study highlights the potential challenges of applying a leave-one-out cross-validation approach and provides a scientific foundation for the feasibility of different ensemble learning algorithms and cross-validation approaches for accurate AGB estimation.

Assessment of Forest Biomass and Carbon Storage in Habitat 9340 Quercus ilex L. to Support Management Decisions for Climate Change Mitigation

The assessment of forest biomass has been a focus of research, aiming to understand matter–energy relationships in forest ecosystems and address forestry practice issues. In recent decades there has been increased societal interest in rational forest resource exploitation, necessitating accurate biomass estimation. In Greece there has been limited efforts in estimating forest biomass, and the current study focuses on habitat type 9340, “Quercus ilex and Quercus rotundifolia forests,” located in the protected areas “GR1420004–Karla–Mavrovouni–Kefalovryso Velestinou–Neochori” and “GR1430001–Oros Pilio and Paraktia Thalassia Zoni (Mount Pilion and Coastal Sea Zone)” in the Natura 2000 network. The habitat falls within the thermo-Mediterranean zone and the study aims to estimate the biomass and carbon storage to contribute to sustainable EU forest strategies. Due to resource limitations, a generalized allometric equation was proposed as an alternative to traditional biomass estimation methods. The above-ground biomass per hectare was estimated, ranging from 16.10 to 205.27 Mg ha−1 (mean 61.91 Mg ha−1). Furthermore, two approaches were used to estimate the total biomass in the habitat: regional averages based on spatial distribution and spatial interpolation using a geographic information system. The total estimated biomass for habitat 9340 is 183,505 Mg, with the carbon storage in standing dry biomass amounting to 83,725.25 Mg. Despite the absence of sampled biomass specimens, this study combines robust statistical techniques with published empirical values to provide a solid framework for estimating assimilated CO2. Sequestered CO2 in the study area is estimated at 306,992.58 Mg. Therefore, the significant role of Quercus ilex L. in carbon storage in Mediterranean forest ecosystems is highlighted by sequestering a substantial amount of CO2.

Improved random forest algorithms for increasing the accuracy of forest aboveground biomass estimation using Sentinel-2 imagery

A simpler, unbiased, and comprehensive random forest (RF) model is needed to improve the accuracy of aboveground biomass (AGB) estimation. In this study, data were obtained from 128 sample plots of Pinus yunnanensis forest located in Chuxiong prefecture, Yunnan province, China. Sentinel-2 imagery data were applied to extract the important predictors of forest AGB, which were screened using the Boruta algorithm. We compared the fitting performance of two modified random forest models − regularized random forest (RRF) and quantile random forest (QRF) − with the random forest model. Moreover, we combined the smallest mean error of each quantile model as the best QRF (QRFb). The result showed: (1) Window sizes of 3 × 3 pixels and 5 × 5 pixels demonstrated greater sensitivity and suitability for estimating AGB than the 7 × 7 pixels window size. Enhanced vegetation indices derived from Red Edge 1 (B5) and Near-Infrared bands (B8A) were strongly correlated with AGB, indicating the heightened sensitivity of B5 and B8A bands to biomass and their potential in AGB estimation. (2) The RRF model outperformed both the standard RF and QRF in fitting performance, with an R2 of 0.56 and RMSE 57.14 Mg/ha. (3) The QRFb model exhibited the highest R2 of 0.88 and lowest RMSE of 29.56 Mg/ha, significantly reducing overestimation and underestimation issues. The modified RF regression supplies new insights into improving forest AGB estimation, which will be helpful for future research addressing carbon cycling.